Scale Equivariance Regularization and Feature Lifting in High Dynamic Range Modulo Imaging
This work addresses reconstruction challenges in high dynamic range imaging for applications like photography and computer vision, representing a strong specific gain.
The paper tackled the problem of accurate high dynamic range reconstruction in modulo imaging, which suffers from ambiguities between natural edges and artificial wrap discontinuities, and achieved state-of-the-art performance across perceptual and linear HDR quality metrics.
Modulo imaging enables high dynamic range (HDR) acquisition by cyclically wrapping saturated intensities, but accurate reconstruction remains challenging due to ambiguities between natural image edges and artificial wrap discontinuities. This work proposes a learning-based HDR restoration framework that incorporates two key strategies: (i) a scale-equivariant regularization that enforces consistency under exposure variations, and (ii) a feature lifting input design combining the raw modulo image, wrapped finite differences, and a closed-form initialization. Together, these components enhance the network's ability to distinguish true structure from wrapping artifacts, yielding state-of-the-art performance across perceptual and linear HDR quality metrics.